Triple
T14066122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Château-Thierry |
E338474
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Písek |
E424693
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Písek | Statement: [Château-Thierry, hasTwinTown, Písek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Písek Context triple: [Château-Thierry, hasTwinTown, Písek]
-
A.
Písek
chosen
Písek is a historic town in the South Bohemian Region of the Czech Republic, known for its medieval stone bridge and well-preserved old town.
-
B.
Šmicer
Šmicer is a Czech surname most notably associated with former professional footballer Vladimír Šmicer, who played for clubs such as Slavia Prague and Liverpool and represented the Czech national team.
-
C.
Kája
Kája is a Czech diminutive form of the given name Karel.
-
D.
Krupa
Krupa is a surname most famously associated with Gene Krupa, the pioneering American jazz and big band drummer.
-
E.
Tato
Tato was an early Lombard king of the Lething dynasty, known from tradition as a pre-migration ruler in the tribe’s legendary history.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de568b81f08190a571004261c0e8e4 |
completed | April 14, 2026, 3 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb669111081909ccd167f41571a00 |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:21 p.m.